© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 114492
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.65
    inSlope
    -0.59
    tanleria
    -0.49
    UpInside
    -0.45
    httphttps
    -0.43
     للاسماء
    -0.42
    তথ্যসূত্র
    -0.41
     ligiloj
    -0.41
     становника
    -0.41
    HomeAsUpEnabled
    -0.40
    POSITIVE LOGITS
    yntaxException
    0.42
    ThroughAttribute
    0.41
     restTemplate
    0.40
     garantías
    0.39
    voltaic
    0.37
     analytical
    0.36
     Analytical
    0.35
     '{@
    0.35
    mingo
    0.34
    twimg
    0.34
    Activations Density 1.103%

    No Known Activations